Ocrolus raises $24 million to scan financial documents with computer vision

Ocrolus, a New York startup that taps AI and machine learning to parse financial documents, today announced it has raised $24 million in a series B round led by venture growth equity firm Oak HC/FT. Ocrolus cofounder and CEO Sam Bobley said the fresh capital, which follows a $4 million series A in April 2018 and brings the company’s total raised to about $30 million, will fuel expansion into verticals like consumer and auto lending and advance development of the company’s underwriting solutions for banks.

“Sometimes humans are better than robots,” said Bobley, who added that Ocrolus has quintupled in size since April 2018 and now counts hundreds of financial services companies among its customer base. “We combine machine processes with live human intelligence to provide customers with a complete solution. The capital will be used to develop workflows for new document types and sharpen our fraud detection and analytical capabilities.”

Ocrolus’ optical character recognition (OCR) technology — which it claims can analyze files with 99% accuracy — supports documents of almost any type and quality. Customers upload files or scans through Ocrolus’ bespoke web portal, after which the company’s backend algorithms extract key information before sending on anonymized snippets to a human team for validation. Finally, the results are delivered to customers’ back-office system.

In that respect, Ocrolus’ offering is a lot like Amazon Web Services’ (AWS) Textract, which uses machine learning to parse data tables, forms, and whole pages for text and data. London-based Flux offers a comparable file-parsing service targeted at retailers, and Upflow’s tech leverages OCR to autonomously detect and extract customer names, amounts, due dates, and more from invoices.

But as chief operating officer Vik Dua explains, Ocrolus’ focus is narrower in scope, which enables it to address domain-specific problems that commonly throw other platforms for a loop. “Our infrastructure is highly scalable and continually teaches itself to become smarter,” he added. “We’re excited to accelerate our product roadmap and alleviate additional pain points for our customers. Ocrolus is poised to improve the quality of work in use cases across financial services and beyond.”

Ocrolus offers a turnkey solution hosted on AWS. The platform reviews bank e-statements, scans, and cell phone pictures of printed statements and generates custom-tailored analytics, ultimately geared toward tracking account balances, detecting money movement, and identifying missing or fraudulent information. Its API plugs into Salesforce and other customer relationship management platforms, and it guarantees a baseline level of security with 256-bit AES encryption, SSL authentication, and multifactor authentication.

“Ocrolus is a unique company providing a rare combination of smart automation, analytics, and accuracy in its solution,” said Oak HC/FT venture partner Dan Petrozzo. “By combining its tremendous technology with an added human touch where required, the platform delivers amazing results for its customers.”